Product Compare
NVIDIA GeForce RTX 4070 GDDR6 vs AMD Radeon Instinct MI100
| GPU | GPU | |
|---|---|---|
| Graphics Card | ||
| Release Date | Aug 2024 | Nov 2020 |
| Generation | GeForce 40 | Radeon Instinct |
| Type | Desktop | Professional |
| Bus Interface | PCIe 4.0 x16 | PCIe 4.0 x16 |
| Clock Speeds | ||
| Base Clock | 1920 MHz | 1000 MHz |
| Boost Clock | 2475 MHz | 1502 MHz |
| Memory Clock | 2500 MHz | 1200 MHz |
| Memory | ||
| Memory Size | 12GB | 32GB |
| Memory Type | GDDR6 | HBM2 |
| Memory Bus | 192bit | 4096bit |
| Bandwidth | 480.0GB/s | 1229GB/s |
| Render Config | ||
| SM Count | 46 | |
| Shading Units | 5888 | 7680 |
| TMUs | 184 | 480 |
| ROPs | 64 | 64 |
| Tensor Cores | 184 | |
| RT Cores | 46 | |
| L1 Cache | 128 KB (per SM) | 16 KB (per CU) |
| L2 Cache | 36 MB | 8 MB |
| Compute Units | 120 | |
| Theoretical Performance | ||
| Pixel Rate | 158.4 GPixel/s | 96.13 GPixel/s |
| Texture Rate | 455.4 GTexel/s | 721.0 GTexel/s |
| FP16 (half) | 29.15 TFLOPS | 184.6 TFLOPS |
| FP32 (float) | 29.15 TFLOPS | 23.07 TFLOPS |
| FP64 (double) | 455.4 GFLOPS | 11.54 TFLOPS |
| Graphics Processor | ||
| GPU Name | AD104 | Arcturus |
| GPU Variant | AD104-2XX-A1 | Arcturus XL |
| Architecture | Ada Lovelace | CDNA 1.0 |
| Foundry | TSMC | TSMC |
| Process Size | 5 nm | 7 nm |
| Transistors | 35.8 billion | 25.6 billion |
| Die Size | 294 mm² | 750 mm² |
| Board Design | ||
| TDP | 200W | 300W |
| Suggested PSU | 550 W | 700 W |
| Outputs | 1x HDMI 2.13x DisplayPort 1.4a | No outputs |
| Power Connectors | 1x 16-pin | 2x 8-pin |
| Graphics Features | ||
| DirectX | 12 Ultimate (12_2) | N/A |
| OpenGL | 4.6 | N/A |
| OpenCL | 3.0 | 2.1 |
| Vulkan | 1.3 | N/A |
| CUDA | 8.9 | |
| Shader Model | 6.8 | N/A |